{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RBGUYHS6HQYBM4X6ASB7TTQAT2","short_pith_number":"pith:RBGUYHS6","schema_version":"1.0","canonical_sha256":"884d4c1e5e3c301672fe0483f9ce009e890b72f751b506f321397513ebea427b","source":{"kind":"arxiv","id":"2604.05738","version":2},"attestation_state":"computed","paper":{"title":"MedLayBench-V: A Large-Scale Benchmark for Expert-Lay Semantic Alignment in Medical Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MedLayBench-V introduces the first large-scale benchmark for expert-lay semantic alignment in medical vision-language models.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Jang, Heeseong Eum, Junhyeok Lee, Kyu Sung Choi","submitted_at":"2026-04-07T11:39:41Z","abstract_excerpt":"Medical Vision-Language Models (Med-VLMs) have achieved expert-level proficiency in interpreting diagnostic imaging. However, current models are predominantly trained on professional literature, limiting their ability to communicate findings in the lay register required for patient-centered care. While text-centric research has actively developed resources for simplifying medical jargon, there is a critical absence of large-scale multimodal benchmarks designed to facilitate lay-accessible medical image understanding. To bridge this resource gap, we introduce MedLayBench-V, the first large-scal"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":true},"canonical_record":{"source":{"id":"2604.05738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-07T11:39:41Z","cross_cats_sorted":[],"title_canon_sha256":"6fda5aa09824ce76fb521ad8bd2a625c824ab973caa211793ee67ad216fc5b56","abstract_canon_sha256":"d01378021905cd301b2bf85640028a6db59a922418f11804523ef31eed4495f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:17:52.889767Z","signature_b64":"FVOfUyD9OfmcUuMLPWa8VtGczvyELLNy1Mb+Z6E7t3SnRM7mq1b+hXJk5AZasvhyuQYOOX6d752T4aFNHW6uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"884d4c1e5e3c301672fe0483f9ce009e890b72f751b506f321397513ebea427b","last_reissued_at":"2026-06-25T01:17:52.889264Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:17:52.889264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedLayBench-V: A Large-Scale Benchmark for Expert-Lay Semantic Alignment in Medical Vision Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"MedLayBench-V introduces the first large-scale benchmark for expert-lay semantic alignment in medical vision-language models.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Jang, Heeseong Eum, Junhyeok Lee, Kyu Sung Choi","submitted_at":"2026-04-07T11:39:41Z","abstract_excerpt":"Medical Vision-Language Models (Med-VLMs) have achieved expert-level proficiency in interpreting diagnostic imaging. However, current models are predominantly trained on professional literature, limiting their ability to communicate findings in the lay register required for patient-centered care. While text-centric research has actively developed resources for simplifying medical jargon, there is a critical absence of large-scale multimodal benchmarks designed to facilitate lay-accessible medical image understanding. To bridge this resource gap, we introduce MedLayBench-V, the first large-scal"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we introduce MedLayBench-V, the first large-scale multimodal benchmark dedicated to expert-lay semantic alignment. ... constructed via a Structured Concept-Grounded Refinement (SCGR) pipeline. This method enforces strict semantic equivalence by integrating Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) with micro-level entity constraints.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the SCGR pipeline, by integrating UMLS CUIs with micro-level entity constraints, will enforce strict semantic equivalence between expert and lay descriptions without information loss, hallucination, or incomplete coverage of medical concepts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MedLayBench-V is the first large-scale multimodal benchmark for expert-lay semantic alignment in medical vision-language models, constructed via a Structured Concept-Grounded Refinement pipeline that uses UMLS CUIs to enforce equivalence.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MedLayBench-V introduces the first large-scale benchmark for expert-lay semantic alignment in medical vision-language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"858c260b75078abb81f9f7286cb0499c5923b8459fadcca07545e98498fc3c4e"},"source":{"id":"2604.05738","kind":"arxiv","version":2},"verdict":{"id":"99e95158-bc04-4b93-b753-6146e0759c01","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:32:26.921463Z","strongest_claim":"we introduce MedLayBench-V, the first large-scale multimodal benchmark dedicated to expert-lay semantic alignment. ... constructed via a Structured Concept-Grounded Refinement (SCGR) pipeline. This method enforces strict semantic equivalence by integrating Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) with micro-level entity constraints.","one_line_summary":"MedLayBench-V is the first large-scale multimodal benchmark for expert-lay semantic alignment in medical vision-language models, constructed via a Structured Concept-Grounded Refinement pipeline that uses UMLS CUIs to enforce equivalence.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the SCGR pipeline, by integrating UMLS CUIs with micro-level entity constraints, will enforce strict semantic equivalence between expert and lay descriptions without information loss, hallucination, or incomplete coverage of medical concepts.","pith_extraction_headline":"MedLayBench-V introduces the first large-scale benchmark for expert-lay semantic alignment in medical vision-language models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.05738/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"36129d9fd642d8517c54fa8415c081880eb4090561df8f7b404ee469acf76040"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.05738","created_at":"2026-06-25T01:17:52.889339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.05738v2","created_at":"2026-06-25T01:17:52.889339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.05738","created_at":"2026-06-25T01:17:52.889339+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBGUYHS6HQYB","created_at":"2026-06-25T01:17:52.889339+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBGUYHS6HQYBM4X6","created_at":"2026-06-25T01:17:52.889339+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBGUYHS6","created_at":"2026-06-25T01:17:52.889339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2","json":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2.json","graph_json":"https://pith.science/api/pith-number/RBGUYHS6HQYBM4X6ASB7TTQAT2/graph.json","events_json":"https://pith.science/api/pith-number/RBGUYHS6HQYBM4X6ASB7TTQAT2/events.json","paper":"https://pith.science/paper/RBGUYHS6"},"agent_actions":{"view_html":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2","download_json":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2.json","view_paper":"https://pith.science/paper/RBGUYHS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.05738&json=true","fetch_graph":"https://pith.science/api/pith-number/RBGUYHS6HQYBM4X6ASB7TTQAT2/graph.json","fetch_events":"https://pith.science/api/pith-number/RBGUYHS6HQYBM4X6ASB7TTQAT2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2/action/storage_attestation","attest_author":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2/action/author_attestation","sign_citation":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2/action/citation_signature","submit_replication":"https://pith.science/pith/RBGUYHS6HQYBM4X6ASB7TTQAT2/action/replication_record"}},"created_at":"2026-06-25T01:17:52.889339+00:00","updated_at":"2026-06-25T01:17:52.889339+00:00"}